Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Towards Versatile Embodied Navigation
Hanqing Wang, Wei Liang, Luc Van Gool, Wenguan Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| train jointly on four tasks instead of one (multitask) | Vienna MT · VLN val unseen | SR: 14.3 -> 16.3 | Improved |
| multitask training for Seq2Seq | Seq2Seq · VLN val unseen | SR: 5.2 -> 7.6 | Improved |
| multitask training | Vienna MT · Object-goal nav val seen | SR: 33.2 -> 33.3 | No clear effect |
| add audio to RGBD (ablation) | Vienna MT · VLN val unseen | SR: 12.5 -> 16.3 | Improved |
| add audio to RGBD (ablation) | Vienna MT · Audio-goal nav val unseen | SR: 2.3 -> 18.7 | Improved |
| add task embeddings to episodic target (ablation) | Vienna MT · Audio-goal nav val unseen | SR: 17.2 -> 18.7 | Improved |
| add task embeddings to episodic target (ablation) | Vienna MT · VLN val unseen | SR: 14.1 -> 16.3 | Improved |
| increase target embeddings N from 1 to 5 (ablation) | Vienna MT · Audio-goal nav val unseen | SR: 15.6 -> 18.7 | Improved |
| increase target embeddings N from 5 to 7 (ablation) | Vienna MT · Audio-goal nav val unseen | SR: 18.7 -> 18.3 | No clear effect |
| share 2 layers of planner trunk instead of separate (ablation) | Vienna MT · Audio-goal nav val unseen | SR: 17.4 -> 18.7 | Improved |
| share all planner layers instead of 2 (ablation) | Vienna MT · Audio-goal nav val unseen | SR: 18.7 -> 17.6 | Hurt |
| add progress, slack, explore rewards to success reward (ablation) | Vienna MT · Audio-goal nav val unseen | SR: 1.5 -> 18.7 | Improved |
Closest papers by meaning
- NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models (AAAI 2024 · similarity 0.90)
- NavBench: Probing Multimodal Large Language Models for Embodied Navigation (NeurIPS 2025 · similarity 0.89)
- Image2Sim: Scaling Embodied Navigation via Generative Neural Simulator (NeurIPS 2026 · similarity 0.89)
- RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation (NeurIPS 2026 · similarity 0.89)
- Towards Learning a Generalist Model for Embodied Navigation (CVPR 2024 · similarity 0.89)
- Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
